Making caches work for graph analytics
© 2017 IEEE. Large-scale applications implemented in today's high performance graph frameworks heavily underutilize modern hardware systems. While many graph frameworks have made substantial progress in optimizing these applications, we show that it is still possible to achieve up to 5× speedup...
Main Authors: | Zhang, Yunming, Kiriansky, Vladimir, Mendis, Charith, Amarasinghe, Saman, Zaharia, Matei |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
IEEE
2021
|
Online Access: | https://hdl.handle.net/1721.1/137371 |
Similar Items
-
goSLP: globally optimized superword level parallelism framework
by: Mendis, Charith, et al.
Published: (2021) -
DAWG: A Defense Against Cache Timing Attacks in Speculative Execution Processors
by: Kiriansky, Vladimir L.(Vladimir Lubenov), et al.
Published: (2020) -
All You Need Is Superword-Level Parallelism: Systematic Control-Flow Vectorization with SLP
by: Chen, Yishen, et al.
Published: (2022) -
GraphIt: a high-performance graph DSL
by: Zhang, Yunming, et al.
Published: (2021) -
Optimizing ordered graph algorithms with GraphIt
by: Zhang, Yunming, et al.
Published: (2021)